feat(latest): extract per-site covers (#58)

backend/internal/latest/sites.go

@@ -1,6 +1,7 @@
 package latest
 
 import (
+	"html"
 	"net/url"
 	"regexp"
 	"strconv"
@@ -146,3 +147,79 @@ func latestChapterFrom(site, seriesURL, body string) (latestChapter, bool) {
 	}
 	return best, found
 }
+
+var metaTagRe = regexp.MustCompile(`(?is)<meta\b[^>]*>`)
+var doubleQuotedMetaAttrRe = regexp.MustCompile(`(?is)([a-z][a-z0-9:_-]*)\s*=\s*"([^"]*)"`)
+var singleQuotedMetaAttrRe = regexp.MustCompile(`(?is)([a-z][a-z0-9:_-]*)\s*=\s*'([^']*)'`)
+
+// comix stores its cover in the target series object in the page state rather
+// than an HTML metadata tag. The medium rendition is deliberately selected
+// instead of deriving a URL for a thumbnail or retaining the larger rendition.
+var comixHIDRe = regexp.MustCompile(`"hid"\s*:\s*"[^"]+"`)
+var comixPosterMediumRe = regexp.MustCompile(`(?s)"poster"\s*:\s*\{.*?"medium"\s*:\s*"([^"]+)"`)
+
+// kagane's browser-fetched series response carries this published cover URL.
+// Match the cover field, not merely an image-shaped URL elsewhere in JSON.
+var kaganeCoverFieldRe = regexp.MustCompile(`"cover"\s*:\s*"([^"]+)"`)
+
+func comixCoverURL(seriesURL, body string) string {
+	m := comixSlugRe.FindStringSubmatch(seriesURL)
+	if m == nil {
+		return ""
+	}
+	id := m[1]
+	if i := strings.Index(id, "-"); i != -1 {
+		id = id[:i]
+	}
+	hidRe := regexp.MustCompile(`"hid"\s*:\s*"` + regexp.QuoteMeta(id) + `"`)
+	hid := hidRe.FindStringIndex(body)
+	if hid == nil {
+		return ""
+	}
+	end := len(body)
+	if next := comixHIDRe.FindStringIndex(body[hid[1]:]); next != nil {
+		end = hid[1] + next[0]
+	}
+	if m := comixPosterMediumRe.FindStringSubmatch(body[hid[0]:end]); m != nil {
+		return publishedCoverURL(m[1])
+	}
+	return ""
+}
+
+func coverFrom(site, seriesURL, body string) (string, bool) {
+	var cover string
+	switch site {
+	case "asura", "demonic", "lightnovelworld":
+		cover = metaContent(body, "property", "og:image")
+	case "novelfull":
+		cover = metaContent(body, "name", "image")
+	case "comix":
+		cover = comixCoverURL(seriesURL, body)
+	case "kagane":
+		if m := kaganeCoverFieldRe.FindStringSubmatch(body); m != nil {
+			cover = publishedCoverURL(m[1])
+		}
+	}
+	return cover, cover != ""
+}
+
+func metaContent(body, attrName, attrValue string) string {
+	for _, tag := range metaTagRe.FindAllString(body, -1) {
+		attrs := make(map[string]string)
+		for _, m := range doubleQuotedMetaAttrRe.FindAllStringSubmatch(tag, -1) {
+			attrs[strings.ToLower(m[1])] = m[2]
+		}
+		for _, m := range singleQuotedMetaAttrRe.FindAllStringSubmatch(tag, -1) {
+			attrs[strings.ToLower(m[1])] = m[2]
+		}
+		if strings.EqualFold(attrs[strings.ToLower(attrName)], attrValue) {
+			return publishedCoverURL(attrs["content"])
+		}
+	}
+	return ""
+}
+
+func publishedCoverURL(value string) string {
+	value = strings.TrimSpace(html.UnescapeString(value))
+	return strings.ReplaceAll(value, " ", "%20")
+}